forked from roger/k3s-cluster
set platform engineer url to platform-engineer.rogi.casa
This commit is contained in:
@@ -50,11 +50,11 @@ data:
|
||||
api_key: "sk-no-auth"
|
||||
# Faster "flash" variant: Qwen3.6-35B-A3B is a MoE (3B active params), so
|
||||
# inference is much faster than the dense 27B despite more total weights.
|
||||
# See llamacpp/deployment-qwen36-36b-a3b.yaml.
|
||||
- model_name: qwen3.6-36b-a3b
|
||||
# See llamacpp/deployment-qwen36-35b-a3b.yaml.
|
||||
- model_name: qwen3.6-35b-a3b
|
||||
litellm_params:
|
||||
model: openai/qwen3.6-36b-a3b
|
||||
api_base: http://llamacpp-qwen36-36b-a3b.llamacpp/v1
|
||||
model: openai/qwen3.6-35b-a3b
|
||||
api_base: http://llamacpp-qwen36-35b-a3b.llamacpp/v1
|
||||
api_key: "sk-no-auth"
|
||||
litellm_settings:
|
||||
#set_verbose: True # Uncomment this if you want to see verbose logs; not recommended in production
|
||||
|
||||
Reference in New Issue
Block a user